A model training, energy efficiency prediction method, device, medium and program product

Abstract

The present invention discloses a model training, energy efficiency prediction method, device, medium and program product in the field of computer technology. The present invention constructs model training data with partial configuration combinations and non-full load energy efficiency test results, and trains to obtain an energy efficiency prediction model. The energy efficiency prediction model can be used to realize server energy efficiency prediction without the need to perform a full load test on the server after each configuration of the server BIOS option, saving computer resources and test time, and the energy efficiency prediction model can improve the accuracy of the test results; the model training data for training the energy efficiency prediction model is obtained based on partial configuration combinations and non-full load tests in multiple configuration combinations formed by various configuration items to be tested of the basic input and output system, and the selection of partial configuration combinations and non-full load tests can reduce the amount of data processing, improve the model training efficiency, save computer resources, and further improve the efficiency and accuracy of server energy efficiency testing.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a model training, energy efficiency prediction method, device, medium and program product. Background Art

[0002] At present, server energy efficiency evaluation tools are generally used to test servers, which can measure server energy efficiency by comprehensively analyzing performance and energy consumption indicators. Using server energy efficiency evaluation tools requires full load testing of the server after configuring the server BIOS (Basic Input Output System) options each time, which takes a lot of time, and the accuracy of the test results depends on the accuracy of data collection.

[0003] Therefore, how to improve the efficiency and accuracy of server energy efficiency testing is a problem that technical personnel in this field need to solve. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a model training, energy efficiency prediction method, device, medium and program product to improve the efficiency and accuracy of server energy efficiency testing. The specific scheme is as follows:

[0005] In a first aspect, the present invention provides a model training method, which is applied to a test control system, comprising:

[0006] Determine multiple configuration combinations formed by configuration items to be tested of the basic input and output system;

[0007] Selecting some configuration combinations from the multiple configuration combinations, calling an energy efficiency test tool to perform a non-full load test on the selected configuration combinations, and collecting corresponding energy efficiency test results output by the energy efficiency test tool; the degree of similarity between the energy efficiency test results of the non-full load test and the full load test is greater than a preset threshold;

[0008] The selected configuration combinations and corresponding energy efficiency test results are constructed into the same data group to obtain multiple data groups;

[0009] Model training data is constructed based on adjacent data groups in the multiple data groups, and an energy efficiency prediction model is trained using the model training data.

[0010] Optionally, determining a plurality of configuration combinations formed by configuration items to be tested of the basic input / output system includes:

[0011] Determine each configuration item to be tested of the basic input / output system and the configuration value corresponding to each configuration item to be tested;

[0012] The configuration values corresponding to the configuration items to be tested are respectively combined without duplication to obtain the multiple configuration combinations.

[0013] Optionally, selecting some of the multiple configuration combinations includes:

[0014] Selecting some of the multiple configuration combinations according to a preset ratio; the preset ratio is not less than fifty percent.

[0015] Optionally, selecting some of the multiple configuration combinations includes:

[0016] Sorting the multiple configuration combinations to obtain a target sequence;

[0017] Selecting configuration combinations at intervals in the target sequence.

[0018] Optionally, selecting configuration combinations at intervals in the target sequence includes:

[0019] Taking the configuration combinations arranged at even positions in the target sequence as the selected configuration combinations; or taking the configuration combinations arranged at odd positions in the target sequence as the selected configuration combinations.

[0020] Optionally, calling an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations includes:

[0021] Determining each test task corresponding to the full-load test according to the task configuration file of the energy efficiency test tool, and selecting some of the test tasks from the various test tasks;

[0022] Calling the energy efficiency test tool to run the selected test tasks to perform a non-full-load test on the selected configuration combinations.

[0023] Optionally, selecting some of the test tasks from the various test tasks includes:

[0024] Selecting some of the test tasks from the various test tasks according to a preset non-full-load test table in the task configuration file.

[0025] Optionally, selecting some of the test tasks from the various test tasks includes:

[0026] Randomly selecting test tasks from the various test tasks according to a randomly selected strategy configured in the task configuration file as candidate tasks;

[0027] Calling the energy efficiency test tool to run the candidate tasks to perform a non-full-load test on the selected configuration combinations, and collecting the corresponding energy efficiency test results output by the energy efficiency test tool;

[0028] Selecting, from the obtained energy efficiency test results, the energy efficiency test results with a similarity degree greater than the preset threshold to the energy efficiency test results of the full-load test as optional results;

[0029] Use the candidate task corresponding to the optional result as the selected test task.

[0030] Optionally, construct the selected configuration combination and the corresponding energy efficiency test result into the same data group to obtain multiple data groups, including:

[0031] Concatenate the selected configuration combination and the corresponding energy efficiency test result to obtain multiple corresponding data groups.

[0032] Optionally, construct model training data based on adjacent data groups among the multiple data groups, including:

[0033] Set the unit data size;

[0034] Determine the number of data groups included in adjacent data groups according to the unit data size;

[0035] Construct multiple pieces of the model training data in units of the number of data groups in the multiple data groups.

[0036] Optionally, the value of the number of data groups is 3;

[0037] Correspondingly, construct multiple pieces of the model training data in units of the number of data groups in the multiple data groups, including:

[0038] Concatenate every three adjacent data groups in the multiple data groups in sequence.

[0039] Optionally, concatenate every three adjacent data groups in the multiple data groups in sequence, including:

[0040] Convert each data group in the multiple data groups into one-hot encoding, and concatenate the one-hot encodings of every three adjacent data groups in sequence.

[0041] Optionally, train an energy efficiency prediction model using the model training data, including:

[0042] Input the model training data into a deep learning model so that the deep learning model outputs corresponding training energy efficiency results;

[0043] Calculate the loss value between the training energy efficiency result and the preset energy efficiency label of the model training data;

[0044] If the loss value meets the preset model convergence condition, use the current deep learning model as the energy efficiency prediction model.

[0045] Optionally, if the loss value does not meet the model convergence condition, the model parameters of the current deep learning model are iteratively updated using the loss value until the loss value meets the model convergence condition.

[0046] Optionally, after training an energy efficiency prediction model using the model training data, the method further includes:

[0047] Constructing model application data based on the multiple configuration combinations.

[0048] In a second aspect, the present invention provides an energy efficiency prediction method, including:

[0049] Determining multiple configuration combinations formed by each configuration item to be measured of the basic input / output system;

[0050] Selecting some configuration combinations from the multiple configuration combinations, invoking an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collecting the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results between the non-full-load test and the full-load test is greater than a preset threshold;

[0051] Using the energy efficiency prediction model to predict the energy efficiency of the configuration combinations for which there are no corresponding energy efficiency test results among the multiple configuration combinations, and collecting the corresponding energy efficiency prediction results;

[0052] Wherein, the energy efficiency prediction model is obtained based on the model training method described in any one of the foregoing.

[0053] Optionally, the method further includes:

[0054] Summarizing and analyzing the multiple configuration combinations and their corresponding energy efficiency prediction results to determine the influence relationship between the configuration values corresponding to each configuration item to be measured among the multiple configuration combinations and the corresponding energy efficiency prediction results;

[0055] Visualizing the multiple configuration combinations and their corresponding energy efficiency prediction results using a curve.

[0056] In a third aspect, the present invention provides an electronic device, including:

[0057] A memory for storing a computer program;

[0058] A processor for executing the computer program to implement the method disclosed above.

[0059] In a fourth aspect, the present invention provides a non-volatile storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the method disclosed above.

[0060] Fifth aspect, the present invention provides a computer program product, including a computer program / instructions, which when executed by a processor implement the steps of the corresponding method disclosed above.

[0061] Sixth aspect, the present invention provides a model training device, applied to a test control system, including:

[0062] A first determination module, configured to determine a plurality of configuration combinations formed by each to-be-tested configuration item of the basic input / output system;

[0063] A first test module, configured to select some configuration combinations from the plurality of configuration combinations, call an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collect the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results of the non-full-load test and the full-load test is greater than a preset threshold;

[0064] A construction module, configured to construct the selected configuration combinations and the corresponding energy efficiency test results into the same data group, obtaining a plurality of data groups;

[0065] A training module, configured to construct model training data based on adjacent data groups among the plurality of data groups, and train an energy efficiency prediction model by using the model training data.

[0066] Optionally, the determination module is specifically configured to:

[0067] Determine each to-be-tested configuration item of the basic input / output system and the configuration values respectively corresponding to each to-be-tested configuration item;

[0068] Perform non-repetitive combinations on the configuration values respectively corresponding to each to-be-tested configuration item, obtaining the plurality of configuration combinations.

[0069] Optionally, the test module is specifically configured to:

[0070] Select some configuration combinations from the plurality of configuration combinations according to a preset ratio; the preset ratio is not less than fifty percent.

[0071] Optionally, the test module is specifically configured to:

[0072] Sort the plurality of configuration combinations to obtain a target sequence;

[0073] Select configuration combinations at intervals in the target sequence.

[0074] Optionally, the test module is specifically configured to:

[0075] Use the configuration combinations arranged at even positions in the target sequence as the selected configuration combinations; or use the configuration combinations arranged at odd positions in the target sequence as the selected configuration combinations.

[0076] Optionally, the test module is specifically configured to:

[0077] Determine each test task corresponding to the full-load test according to the task configuration file of the energy efficiency test tool, and select some test tasks from the various test tasks;

[0078] Call the energy efficiency test tool to run the selected test tasks to perform a non-full-load test on the selected configuration combination.

[0079] Optionally, the test module is specifically configured to:

[0080] Select some test tasks from the various test tasks according to the non-full-load test table preset in the task configuration file.

[0081] Optionally, the test module is specifically configured to:

[0082] Randomly select test tasks from the various test tasks according to the random selection strategy configured in the task configuration file as candidate tasks;

[0083] Call the energy efficiency test tool to run the candidate tasks to perform a non-full-load test on the selected configuration combination, and collect the corresponding energy efficiency test results output by the energy efficiency test tool;

[0084] Select, from the obtained energy efficiency test results, the energy efficiency test results whose similarity to the energy efficiency test results of the full-load test is greater than the preset threshold as optional results;

[0085] Use the candidate tasks corresponding to the optional results as the selected test tasks.

[0086] Optionally, the construction module is specifically configured to:

[0087] Concatenate the selected configuration combination with the corresponding energy efficiency test results to obtain a corresponding plurality of data groups.

[0088] Optionally, the construction module is specifically configured to:

[0089] Set the unit data size;

[0090] Determine the number of data groups included in adjacent data groups according to the unit data size;

[0091] Construct a plurality of the model training data in units of the number of data groups among the plurality of data groups.

[0092] Optionally, the value of the number of data groups is 3; correspondingly, the construction module is specifically configured to:

[0093] Concatenate every three adjacent data groups among the plurality of data groups in sequence.

[0094] Optionally, the building block is specifically used to:

[0095] Each data group in the multiple data groups is converted into a one-hot code, and the one-hot codes of every three adjacent data groups are concatenated in sequence.

[0096] Optionally, the training module is specifically used for:

[0097] Inputting the model training data into a deep learning model so that the deep learning model outputs corresponding training energy efficiency results;

[0098] Calculating a loss value between the training energy efficiency result and a preset energy efficiency label of the model training data;

[0099] If the loss value meets the preset model convergence condition, the current deep learning model is used as the energy efficiency prediction model.

[0100] Optionally, the training module is specifically used to: if the loss value does not meet the model convergence condition, use the loss value to iteratively update the model parameters of the current deep learning model until the loss value meets the model convergence condition.

[0101] Optionally, it also includes:

[0102] Another construction module is used to obtain model application data based on the multiple configuration combinations after the energy efficiency prediction model is trained using the model training data.

[0103] In a seventh aspect, the present invention provides an energy efficiency prediction device, comprising:

[0104] A second determination module is used to determine a plurality of configuration combinations formed by various configuration items to be tested of the basic input and output system;

[0105] A second test module is used to select some configuration combinations from the multiple configuration combinations, call the energy efficiency test tool to perform a non-full load test on the selected configuration combinations, and collect corresponding energy efficiency test results output by the energy efficiency test tool; the similarity between the energy efficiency test results of the non-full load test and the full load test is greater than a preset threshold;

[0106] A prediction module, configured to use an energy efficiency prediction model to perform energy efficiency prediction on configuration combinations among the multiple configuration combinations for which there are no corresponding energy efficiency test results, and collect corresponding energy efficiency prediction results;

[0107] Wherein, the energy efficiency prediction model is obtained based on any of the model training methods described above.

[0108] Optionally, it also includes:

[0109] An analysis module for summarizing and analyzing the multiple configuration combinations and their corresponding energy efficiency prediction results to determine the influence relationship between the configuration values corresponding to each configuration item to be tested among the multiple configuration combinations and the corresponding energy efficiency prediction results;

[0110] A display module for visually displaying the multiple configuration combinations and their corresponding energy efficiency prediction results using curves.

[0111] As can be seen from the above solution, the present invention provides a model training method, including: determining multiple configuration combinations formed by each configuration item to be tested of the basic input / output system; selecting some configuration combinations from the multiple configuration combinations, invoking an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collecting the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results of the non-full-load test and the full-load test is greater than a preset threshold; constructing the selected configuration combinations and the corresponding energy efficiency test results into the same data group to obtain multiple data groups; constructing model training data based on adjacent data groups among the multiple data groups, and training an energy efficiency prediction model using the model training data.

[0112] It can be seen that the present invention constructs model training data with some configuration combinations and their non-full-load energy efficiency test results, and trains an energy efficiency prediction model. This energy efficiency prediction model can be used to achieve server energy efficiency prediction without having to perform a full-load test on the server every time the server BIOS options are configured, saving computer resources and test time. Moreover, the energy efficiency prediction model can improve the accuracy of test results; the model training data for training the energy efficiency prediction model is obtained based on some configuration combinations among the multiple configuration combinations formed by each configuration item of the basic input / output system and non-full-load tests. The selection of some configuration combinations and non-full-load tests can both reduce the data processing volume, improve the model training efficiency, save computer resources, and further improve the server energy efficiency test efficiency and accuracy.

[0113] Correspondingly, a model training, energy efficiency prediction device, equipment, medium, and program product provided by the present invention also have the above technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0114] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0115] Figure 1 It is a flowchart of a model training method disclosed by the present invention;

[0116] Figure 2 A flow chart of an energy efficiency prediction method disclosed in the present invention;

[0117] Figure 3 A schematic diagram of an energy efficiency test scheme disclosed in the present invention;

[0118] Figure 4 A schematic diagram of energy efficiency prediction using a model disclosed in the present invention;

[0119] Figure 5 A schematic diagram of a BIOS combination and a corresponding energy efficiency curve disclosed in the present invention;

[0120] Figure 6 A schematic diagram of the structure of an energy efficiency prediction model disclosed in the present invention;

[0121] Figure 7 A schematic diagram of an electronic device disclosed in the present invention;

[0122] Figure 8 A server structure diagram provided by the present invention;

[0123] Figure 9 A terminal structure diagram provided by the present invention. DETAILED DESCRIPTION

[0124] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other examples obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0125] At present, server energy efficiency evaluation tools are generally used to test servers, which can measure server energy efficiency by comprehensively analyzing performance and energy consumption indicators. Using server energy efficiency evaluation tools requires full load testing of the server after configuring the server BIOS options each time, which takes a lot of time, and the accuracy of the test results depends on the accuracy of data collection. To this end, the present invention provides a model training and energy efficiency prediction scheme, which can improve the efficiency and accuracy of server energy efficiency testing.

[0126] See also Figure 1 As shown, an embodiment of the present invention discloses a model training method, which is applied to test a control system, comprising:

[0127] S101, determining a plurality of configuration combinations formed by various configuration items to be tested of a basic input / output system.

[0128] It should be noted that the test control system includes: a program implementing the solution of this embodiment, and this program can interact with the basic input / output system and the energy efficiency test tool. For example: reading the BIOS options and their configuration values of the basic input / output system, calling the energy efficiency test tool, etc.

[0129] In one example, the configuration items to be tested of the basic input / output system may include: Enabled, MinFrequency, Max Frequency, and Custom; the configuration values corresponding to these 4 configuration items can be Disabled or Enabled, then the configuration items to be tested and their corresponding configuration values can be: Enabled_Disabled, Enabled_Enabled, Min Frequency_Disabled, Min Frequency_Enabled, Max Frequency_Disabled, Max Frequency_Enabled, Custom_Disabled, and Custom_Enabled, and a total of 8 configuration combinations can be obtained. Therefore, in one implementation manner, determining the multiple configuration combinations formed by the configuration items to be tested of the basic input / output system includes: determining the configuration items to be tested of the basic input / output system and the configuration values corresponding to each configuration item to be tested respectively; performing non-repeated combinations on the configuration values corresponding to each configuration item to be tested respectively to obtain multiple configuration combinations.

[0130] In one implementation manner, selecting some configuration combinations from the multiple configuration combinations includes: selecting some configuration combinations from the multiple configuration combinations according to a preset ratio; the preset ratio is not less than fifty percent. For example: randomly selecting 4 configuration combinations from the 8 configuration combinations in the above example.

[0131] In one implementation manner, selecting some configuration combinations from the multiple configuration combinations includes: sorting the multiple configuration combinations to obtain a target sequence; selecting configuration combinations at intervals in the target sequence. Among them, selecting configuration combinations at intervals in the target sequence includes: using the configuration combinations arranged at even positions in the target sequence as the selected configuration combinations; or using the configuration combinations arranged at odd positions in the target sequence as the selected configuration combinations. For example: after arranging the 8 configuration combinations in the above example, selecting the configuration combinations at positions 1, 3, 5, 7 or the configuration combinations at positions 2, 4, 6, 8.

[0132] S102. Select some configuration combinations from the multiple configuration combinations, call the energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collect the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results between the non-full-load test and the full-load test is greater than a preset threshold.

[0133] In this embodiment, the full-load test means that during the test process, all the test tasks corresponding to the full-load test are executed by the server simultaneously; correspondingly, the non-full-load test means that during the test process, some of the test tasks corresponding to the full-load test are executed by the server simultaneously, while other test tasks do not participate in the test process. For example, if there are 11 test tasks corresponding to the full-load test and all 11 test tasks participate in the test, it is a full-load test; otherwise, it is a non-full-load test.

[0134] Among them, the test process can be realized with the help of an energy efficiency evaluation tool. The specific process is as follows: change the BIOS configuration from options such as the BIOS panel and the energy efficiency evaluation tool, and screen out the parameter configuration with the best performance-to-power ratio under all possible parameter configurations; the performance-to-power ratio is calculated according to 11 different workloads (100%, 90%, 80%... 10%, idle, and the utilization rate of its system also decreases in turn). First, sum up the performance calculations for all loads ∑ssj_ops. Secondly, the power meter connected to the system power supply will record the power status of the system in real time, power. Calculate the power consumption of all loads divided by ∑power. Finally, the system will divide the accumulated performance by the power to obtain the performance-to-power ratio, ∑ssj_ops divided by ∑power = Performance to Power Ratio, as the performance-to-power ratio of the server.

[0135] In one implementation, calling an energy efficiency test tool to perform a non-full-load test on the selected configuration combination includes: determining each test task corresponding to the full-load test according to the task configuration file of the energy efficiency test tool, and selecting some test tasks from the each test task; calling the energy efficiency test tool to run the selected test tasks to perform a non-full-load test on the selected configuration combination. Among them, the task configuration file can be read and written through the task configuration function of the energy efficiency test tool. Specifically, the user can modify the task configuration file on the management page of the energy efficiency test tool. Information such as a non-full-load test table and a task selection strategy can be written in the file.

[0136] In one implementation, selecting some test tasks from the each test task includes: selecting some test tasks from the each test task according to the preset non-full-load test table in the task configuration file. The preset non-full-load test table can record in advance: M test tasks whose similarity to the energy efficiency test results of the full-load test is greater than a preset threshold, and M is less than the total number of all test tasks corresponding to the full-load test.

[0137] In one embodiment, selecting some of the test tasks from the respective test tasks includes: randomly selecting test tasks from the respective test tasks according to the random selection strategy (a task selection strategy) configured in the task profile as candidate tasks; invoking the energy efficiency test tool to run the candidate tasks to perform a non-full-load test on the selected configuration combination, and collecting the corresponding energy efficiency test results output by the energy efficiency test tool; selecting, from the obtained energy efficiency test results, the energy efficiency test results whose similarity to the energy efficiency test results of the full-load test is greater than the preset threshold as optional results; and using the candidate tasks corresponding to the optional results as the selected test tasks.

[0138] S103. Construct the selected configuration combination and the corresponding energy efficiency test results into the same data group to obtain multiple data groups.

[0139] In one embodiment, constructing the selected configuration combination and the corresponding energy efficiency test results into the same data group to obtain multiple data groups includes: splicing the selected configuration combination and the corresponding energy efficiency test results to obtain the corresponding multiple data groups.

[0140] S104. Construct model training data based on adjacent data groups in the multiple data groups, and train an energy efficiency prediction model using the model training data.

[0141] In one embodiment, constructing model training data based on adjacent data groups in the multiple data groups includes: setting the unit data size; determining the number of data groups included in the adjacent data groups according to the unit data size; and constructing multiple model training data in units of the number of data groups in the multiple data groups.

[0142] In one embodiment, the value of the number of data groups is 3; correspondingly, constructing multiple model training data in units of the number of data groups in the multiple data groups includes: splicing every three adjacent data groups in the multiple data groups in order. For example: after 8 data groups are arranged in order, the data groups at arrangement positions 1, 2, and 3 are spliced in order into one model training data, the data groups at arrangement positions 2, 3, and 4 are spliced in order into one model training data, the data groups at arrangement positions 3, 4, and 5 are spliced in order into one model training data, and so on.

[0143] In one embodiment, splicing every three adjacent data groups in the multiple data groups in order includes: converting each data group in the multiple data groups into one-hot encoding, and splicing the one-hot encoding of every three adjacent data groups in order.

[0144] In one implementation, an energy efficiency prediction model is trained using model training data, including: inputting the model training data into a deep learning model so that the deep learning model outputs corresponding training energy efficiency results; calculating a loss value between the training energy efficiency results and the preset energy efficiency labels of the model training data; if the loss value meets the preset model convergence condition, using the current deep learning model as the energy efficiency prediction model. If the loss value does not meet the model convergence condition, iteratively update the model parameters of the current deep learning model using the loss value until the loss value meets the model convergence condition. Among them, calculating the loss value between the training energy efficiency results and the preset energy efficiency labels of the model training data includes: using the formula to calculate the loss value between the training energy efficiency results and the preset energy efficiency labels of the model training data; represents the loss value, represents the training energy efficiency results, represents the preset energy efficiency label, and N is the total number of samples participating in the training. Among them, when the number of data groups takes the value of 3, the preset energy efficiency label of the model training data is: the energy efficiency test result of the data group in the middle position in the model training data.

[0145] In one embodiment, after the energy efficiency prediction model is obtained by training the model training data, the method further includes: constructing model application data based on configuration combinations other than the selected configuration combination in the multiple configuration combinations. The model application data is input into the energy efficiency prediction model so that the energy efficiency prediction model outputs the corresponding energy efficiency prediction results. In this way, it is not necessary to actually test all configuration combinations formed by the configuration items to be tested of the basic input and output system. For example, assuming that there are 8 configuration combinations in total, 4 of them can be used to construct model training data. After the energy efficiency prediction model is obtained by training, the energy efficiency prediction model is used to predict the remaining 4 configuration combinations for which there are no energy efficiency test results, and the corresponding energy efficiency prediction results are collected; thus, the energy efficiency test of all configuration combinations can be completed. Among them, the process of constructing model application data includes: arranging multiple configuration combinations to obtain a sequence; in the sequence, a plurality of model application data are constructed with a set number of combinations (the number of combinations should be equal to the number of data groups) as a unit. When the set number of combinations is 3, each three adjacent configuration combinations in the sequence are spliced in sequence to obtain a plurality of model application data. That is, each three adjacent configuration combinations in the sequence constitute a model application data. It can be seen that the model application data does not contain energy efficiency test results, while the model training data contains energy efficiency test results; and when the energy efficiency prediction model performs energy efficiency prediction for a model application data, it refers to the energy efficiency test results of the adjacent configuration combinations of the predicted configuration combination in the current model application data. For example: if every three adjacent configuration combinations constitute a model application data, then the predicted configuration combination is located in the middle position, and its energy efficiency prediction results are predicted with reference to the energy efficiency test results of the two configuration combinations before and after the middle position. In other words: in a model application data, including a predicted configuration combination, other configuration combinations except this predicted configuration combination already have energy efficiency test results. For another example: if every five adjacent configuration combinations constitute a model application data, then the predicted configuration combination is located in the middle position, and its energy efficiency prediction results are predicted with reference to the energy efficiency test results of the four configuration combinations before and after the middle position. If every four adjacent configuration combinations constitute a model application data, then when the predicted configuration combination is in the second position, its energy efficiency prediction result refers to the energy efficiency test results of the previous and next two configuration combinations; when the predicted configuration combination is in the third position, its energy efficiency prediction result refers to the energy efficiency test results of the previous and next two configuration combinations (specifically, the performance-energy consumption ratio) for prediction.

[0146] It can be seen that this embodiment constructs model training data with partial configuration combinations and their non-full load energy efficiency test results, and trains to obtain an energy efficiency prediction model. This energy efficiency prediction model can be used to realize server energy efficiency prediction without the need to perform a full load test on the server after each configuration of the server BIOS option, thereby saving computer resources and testing time, and the energy efficiency prediction model can improve the accuracy of the test results; the model training data for training the energy efficiency prediction model is obtained based on partial configuration combinations and non-full load tests in multiple configuration combinations formed by various configuration items to be tested of the basic input and output system. The selection of partial configuration combinations and non-full load tests can reduce the amount of data processing, improve the model training efficiency, save computer resources, and further improve the efficiency and accuracy of server energy efficiency testing.

[0147] An energy efficiency prediction method provided by an embodiment of the present invention is introduced below. The energy efficiency prediction method described below can be referenced to other embodiments described in this document.

[0148] See also Figure 2 As shown, an embodiment of the present invention discloses an energy efficiency prediction method, comprising:

[0149] S201: Determine a plurality of configuration combinations formed by configuration items to be tested of a basic input / output system.

[0150] S202. Select some configuration combinations from multiple configuration combinations, call the energy efficiency test tool to perform non-full load test on the selected configuration combinations, and collect corresponding energy efficiency test results output by the energy efficiency test tool; the similarity between the energy efficiency test results of the non-full load test and the full load test is greater than a preset threshold.

[0151] S203: Use the energy efficiency prediction model to perform energy efficiency prediction on configuration combinations for which there are no corresponding energy efficiency test results among the multiple configuration combinations, and collect corresponding energy efficiency prediction results.

[0152] In this embodiment, the energy efficiency prediction model is obtained based on the model training method described in any embodiment.

[0153] In one embodiment, multiple configuration combinations and their corresponding energy efficiency prediction results are summarized and analyzed to determine the influence relationship between the configuration values corresponding to each configuration item to be tested in the multiple configuration combinations and the corresponding energy efficiency prediction results; and multiple configuration combinations and their corresponding energy efficiency prediction results are visualized using curves.

[0154] It can be seen that this embodiment uses the prediction model to improve the accuracy of the test results, save computer resources, and improve the efficiency and accuracy of the server energy efficiency test.

[0155] See also Figure 3, An energy efficiency test solution for a server includes functional modules such as parameter configuration, evaluation tool startup, data and model training, and model intelligent decision-making.

[0156] 1. Parameter configuration.

[0157] The user inputs a BIOS option file to be pre-tested, and this file is in json format. For example, the user inputs the following json format content:

[0158] { " UncoreFreqScaling ": [" Enabled ", " Min Frequency", " MaxFrequency", "Custom"]

[0159] "CoreC-States": ["Disabled", "Enabled"]

[0160] }

[0161] In the background, according to the input options, all combinations of these options will be traversed. Here, there are a total of 4×2 = 8 combinations, namely: Enabled_Disabled, Enabled_Enabled, Min Frequency_Disabled, Min Frequency_Enabled, Max Frequency_Disabled, Max Frequency_Enabled, Custom_Disabled, and Custom_Enabled. All combinations are placed in a file and encoded in one-hot form. For example: Enabled_Disabled is encoded in one-hot as a vector of length 8 with the first element being 1 and the other elements being 0; Enabled_Enabled is encoded in one-hot as a vector of length 8 with the second element being 1 and the other elements being 0, for subsequent traversal.

[0162] 2. Start the benchmark evaluation tool.

[0163] Select some BIOS combinations from the 8 combinations in the above example. For example, select 4 of them. According to the parameter values of each combination option, set the BIOS panel parameters accordingly, and start the SPECpower evaluation tool respectively. Only executing 4 BIOS combinations here is to accumulate training data for subsequent model training, and this method can reduce the time to search for the optimal combination. In addition, the 4 BIOS combinations are screened according to the principle of adjacent intervals. For example, sort the 8 combinations from 1 to 8, and select 1 / 3 / 5 / 7 or 2 / 4 / 6 / 8 to execute the SPECpower evaluation tool. The purpose is to ensure that when predicting the remaining combinations, the adjacent trained combinations can be used for prediction, which can ensure the prediction accuracy.

[0164] As Figure 4 shown, here execute the SPECpower evaluation tool on the 4 BIOS option combinations of 1 / 3 / 5 / 7. When predicting the performance energy consumption ratio of the 2nd BIOS option combination, the one-hot encoding of the 3 BIOS option combinations of 1 / 2 / 3 can be used as the input data of the deep learning model. Figure 4 The five-digit numbers corresponding to 1, 3, 5, and 7 in it are: the performance energy consumption ratio of the corresponding BIOS option combination. In addition, when executing SPECpower, not all 11 workloads (i.e., test tasks) are executed, but the load combination with the most consistent change trend of the performance energy consumption ratio among the 11 workloads is selected to participate in the actual SPECpower evaluation. As Figure 5 shown, Figure 5 Among the 60 BIOS combinations shown, the energy efficiency curve corresponding to 9_8_5_2_0 has the highest consistency with the change trend of the energy efficiency curve corresponding to 11 full loads.

[0165] 3. Data and model training.

[0166] Execute the Specpower evaluation tool on the 4 BIOS parameter combinations of 1 / 3 / 5 / 7, and the corresponding evaluation data can be obtained, including the performance, power consumption, load level, etc. values of the server, and further calculate the performance energy consumption ratio accordingly. Here, parameters such as performance and power consumption need to be normalized, and the result of the normalization , where is the original value of the parameter, corresponds to the maximum value of the parameter, and the load level parameter will be preprocessed in the form of one-hot encoding. Similarly, the numerical value of the performance energy consumption ratio obtained from the evaluation will also be normalized in the same way.

[0167] Further, the one-hot encodings of the BIOS option combinations whose energy efficiency test results need to be predicted and their adjacent combinations are spliced together, and after preprocessing, they are used as the input of a neural network based on deep learning (the initial model to be trained). Considering that the energy efficiency of neighboring BIOS options may be related, splicing adjacent combinations can improve accuracy and enable the model to mine the energy efficiency relationship between neighboring combinations.

[0168] In one example, the structure of the model can be as Figure 6 shown, including: an input layer, two hidden layers, and an output layer. Among them, the loss function uses the cross-entropy loss function: ; where is the true value of the performance energy consumption ratio, is the performance energy consumption ratio value predicted by the model.

[0169] 4. Model output and decision-making.

[0170] After completing the training of the model, an energy efficiency prediction model can be obtained. Then, the energy efficiency prediction model can be used to predict the energy efficiency of the remaining 4 BIOS parameter combinations. In this example, the energy efficiency test results (SPECpower real evaluation data) of the 4 BIOS option combinations of 1 / 3 / 5 / 7 are known. Then, the model is used to predict the energy efficiency of the 4 combinations of 2 / 4 / 6 / 8. From this, the combination with the largest performance energy consumption ratio can be determined from the 8 combinations as the optimal BIOS parameter combination in this test.

[0171] Further, after obtaining all the performance energy consumption ratios evaluated by the SPECpower tool and the performance energy consumption ratios predicted by the model, the parameter combinations of these BIOS options and their corresponding performance energy consumption ratios can be automatically analyzed to determine which BIOS option values have a greater impact on performance, energy consumption, and performance energy consumption ratio respectively. And through a visual interface, it can help users understand the influence trend of the change of a certain BIOS parameter value on several observed values of performance, energy consumption, and performance energy consumption ratio. It provides a more convenient and efficient analysis method for users to understand the BIOS characteristics.

[0172] In this embodiment, to improve the efficiency of screening the optimal BIOS parameter combination by the SPECpower test, the model training samples are sampled, and the number of test loads is also screened. The encoding information of adjacent BIOS options is also added to the model input, which can help the model more accurately predict the performance energy consumption ratio of the BIOS options to be predicted. Finally, the parameter combinations of all options and their corresponding performance energy consumption ratios are automatically analyzed, and the BIOS option values that have a greater impact on performance, energy consumption, and performance energy consumption ratio can be determined.

[0173] A model training device provided in an embodiment of the present invention is introduced below. The model training device described below can be referenced to other embodiments described in this document.

[0174] The embodiment of the present invention discloses a model training device, which is applied to test a control system, including:

[0175] A first determination module is used to determine a plurality of configuration combinations formed by various configuration items to be tested of the basic input and output system;

[0176] A first test module is used to select some configuration combinations from multiple configuration combinations, call an energy efficiency test tool to perform a non-full load test on the selected configuration combination, and collect corresponding energy efficiency test results output by the energy efficiency test tool; the similarity between the energy efficiency test results of the non-full load test and the full load test is greater than a preset threshold;

[0177] A construction module, used to construct the selected configuration combination and the corresponding energy efficiency test results into the same data group to obtain multiple data groups;

[0178] The training module is used to construct model training data based on adjacent data groups in multiple data groups, and use the model training data to train an energy efficiency prediction model.

[0179] In one implementation, the determination module is specifically configured to:

[0180] Determine each configuration item to be tested of the basic input and output system and the configuration value corresponding to each configuration item to be tested;

[0181] The configuration values corresponding to the configuration items to be tested are combined without duplication to obtain multiple configuration combinations.

[0182] In one embodiment, the test module is specifically used to:

[0183] Select a portion of the configuration combinations from the multiple configuration combinations according to a preset ratio; the preset ratio is not less than fifty percent.

[0184] In one embodiment, the test module is specifically used to:

[0185] Sort multiple configuration combinations to obtain a target sequence;

[0186] Interval selection of configuration combinations in the target sequence.

[0187] In one embodiment, the test module is specifically used to:

[0188] The configuration combination arranged at the even-numbered position in the target sequence is taken as the selected configuration combination; or the configuration combination arranged at the odd-numbered position in the target sequence is taken as the selected configuration combination.

[0189] In one embodiment, the test module is specifically configured to:

[0190] Determine each test task corresponding to the full-load test according to the task configuration file of the energy efficiency test tool, and select some test tasks from the various test tasks;

[0191] Call the energy efficiency test tool to run the selected test tasks to perform a non-full-load test on the selected configuration combination.

[0192] Optionally, the test module is specifically configured to:

[0193] Select some test tasks from the various test tasks according to the non-full-load test table preset in the task configuration file.

[0194] Optionally, the test module is specifically configured to:

[0195] Randomly select test tasks from the various test tasks according to the random selection strategy configured in the task configuration file as candidate tasks;

[0196] Call the energy efficiency test tool to run the candidate tasks to perform a non-full-load test on the selected configuration combination, and collect the corresponding energy efficiency test results output by the energy efficiency test tool;

[0197] Select, from the obtained energy efficiency test results, the energy efficiency test results whose similarity to the energy efficiency test results of the full-load test is greater than the preset threshold as optional results;

[0198] Use the candidate tasks corresponding to the optional results as the selected test tasks.

[0199] In one embodiment, the construction module is specifically configured to:

[0200] Concatenate the selected configuration combination with the corresponding energy efficiency test results to obtain a corresponding plurality of data groups.

[0201] In one embodiment, the construction module is specifically configured to:

[0202] Set the unit data size;

[0203] Determine the number of data groups included in adjacent data groups according to the unit data size;

[0204] Construct a plurality of model training data in units of the number of data groups among the plurality of data groups.

[0205] In one embodiment, the value of the number of data groups is 3; correspondingly, the construction module is specifically configured to:

[0206] Concatenate every three adjacent data groups among the plurality of data groups in sequence.

[0207] In one embodiment, the building blocks are specifically used to:

[0208] Each data group in the multiple data groups is converted into a one-hot code, and the one-hot codes of every three adjacent data groups are concatenated in sequence.

[0209] In one embodiment, the training module is specifically used to:

[0210] Inputting model training data into the deep learning model so that the deep learning model outputs corresponding training energy efficiency results;

[0211] Calculate the loss value between the training energy efficiency result and the preset energy efficiency label of the model training data;

[0212] If the loss value meets the preset model convergence condition, the current deep learning model will be used as the energy efficiency prediction model.

[0213] In one embodiment, the training module is specifically used to: if the loss value does not meet the model convergence conditions, then use the loss value to iteratively update the model parameters of the current deep learning model until the loss value meets the model convergence conditions.

[0214] In one embodiment, it further includes:

[0215] Another construction module is used to construct model application data based on configuration combinations other than the selected configuration combination among multiple configuration combinations after the energy efficiency prediction model is trained using the model training data.

[0216] Among them, for more specific working processes of each module and unit in this embodiment, reference can be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0217] It can be seen that this embodiment provides a model training device, which constructs model training data with partial configuration combinations and their non-full load energy efficiency test results, and trains to obtain an energy efficiency prediction model. This energy efficiency prediction model can be used to realize server energy efficiency prediction without the need to perform a full load test on the server after each configuration of the server BIOS option, thereby saving computer resources and testing time, and the energy efficiency prediction model can improve the accuracy of the test results; the model training data for training the energy efficiency prediction model is obtained based on partial configuration combinations and non-full load tests in multiple configuration combinations formed by each configuration item to be tested of the basic input and output system. The selection of partial configuration combinations and non-full load tests can reduce the amount of data processing, improve the model training efficiency, save computer resources, and further improve the efficiency and accuracy of server energy efficiency testing.

[0218] The following introduces an energy efficiency prediction device provided by an embodiment of the present invention. The energy efficiency prediction device described below can be cross-referred to other embodiments described herein.

[0219] An embodiment of the present invention discloses an energy efficiency prediction device, including:

[0220] A second determination module, configured to determine a plurality of configuration combinations formed by each to-be-tested configuration item of the basic input / output system;

[0221] A second test module, configured to select some configuration combinations from the plurality of configuration combinations, call an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collect the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results between the non-full-load test and the full-load test is greater than a preset threshold;

[0222] A prediction module, configured to use an energy efficiency prediction model to perform energy efficiency prediction on the configuration combinations without corresponding energy efficiency test results among the plurality of configuration combinations, and collect the corresponding energy efficiency prediction results;

[0223] Wherein, the energy efficiency prediction model is obtained based on the model training method described in any embodiment.

[0224] In one implementation manner, it further includes:

[0225] An analysis module, configured to summarize and analyze the plurality of configuration combinations and their corresponding energy efficiency prediction results to determine the influence relationship between the configuration values corresponding to each to-be-tested configuration item among the plurality of configuration combinations and the corresponding energy efficiency prediction results;

[0226] A display module, configured to visually display the plurality of configuration combinations and their corresponding energy efficiency prediction results by using curves.

[0227] Wherein, for the more specific working processes of each module and unit in this embodiment, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details are not described herein again.

[0228] It can be seen that this embodiment provides an energy efficiency prediction device, which improves the accuracy of test results by using a prediction model, saves computer resources, and improves the efficiency and accuracy of server energy efficiency testing.

[0229] The following introduces an electronic device provided by an embodiment of the present invention. The electronic device described below can be cross-referred to other embodiments described herein.

[0230] See Figure 7 As shown, an embodiment of the present invention discloses an electronic device, including:

[0231] A memory 701, configured to store a computer program;

[0232] A processor 702 for executing the computer program to implement the method disclosed in any of the above embodiments.

[0233] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: determining a plurality of configuration combinations formed by each configuration item to be tested of the basic input / output system; selecting some configuration combinations from the plurality of configuration combinations, invoking an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collecting the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results between the non-full-load test and the full-load test is greater than a preset threshold; constructing the selected configuration combinations and the corresponding energy efficiency test results into the same data group to obtain a plurality of data groups; constructing model training data based on adjacent data groups in the plurality of data groups, and training an energy efficiency prediction model by using the model training data.

[0234] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: determining each configuration item to be tested of the basic input / output system and the configuration values respectively corresponding to each configuration item to be tested; performing non-repetitive combinations on the configuration values respectively corresponding to each configuration item to be tested to obtain a plurality of configuration combinations.

[0235] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: selecting some configuration combinations from the plurality of configuration combinations according to a preset ratio; the preset ratio is not less than fifty percent.

[0236] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: sorting the plurality of configuration combinations to obtain a target sequence; selecting configuration combinations at intervals in the target sequence.

[0237] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: using the configuration combinations arranged at even positions in the target sequence as the selected configuration combinations; or using the configuration combinations arranged at odd positions in the target sequence as the selected configuration combinations.

[0238] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: determining each test task corresponding to the full-load test; selecting some test tasks from each test task; using the selected test tasks to invoke an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations.

[0239] In this embodiment, when the processor executes the computer program stored in the memory, the following steps may be specifically implemented: selecting some test tasks from each test task according to a preset non-full-load test table.

[0240] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: randomly select a test task from each test task as a candidate task; use the candidate task to call the energy efficiency test tool to perform a non-full-load test on the selected configuration combination, and collect the corresponding energy efficiency test results output by the energy efficiency test tool; select the energy efficiency test results with a similarity greater than a preset threshold to the energy efficiency test results of the full-load test from the obtained energy efficiency test results as optional results; use the candidate task corresponding to the optional result as the selected test task.

[0241] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: splice the selected configuration combination with the corresponding energy efficiency test results to obtain corresponding multiple data groups.

[0242] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: set the unit data size; determine the number of data groups included in adjacent data groups according to the unit data size; construct multiple model training data in the multiple data groups in units of the number of data groups.

[0243] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: splice every three adjacent data groups in the multiple data groups in sequence.

[0244] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: convert each data group in the multiple data groups into one-hot encoding, and splice the one-hot encoding of every three adjacent data groups in sequence.

[0245] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: input the model training data into the deep learning model so that the deep learning model outputs the corresponding training energy efficiency results; calculate the loss value between the training energy efficiency results and the preset energy efficiency labels of the model training data; if the loss value meets the preset model convergence condition, use the current deep learning model as the energy efficiency prediction model.

[0246] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: if the loss value does not meet the model convergence condition, use the loss value to iteratively update the model parameters of the current deep learning model until the loss value meets the model convergence condition.

[0247] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: constructing model application data based on multiple configuration combinations.

[0248] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: determining multiple configuration combinations formed by each to-be-tested configuration item of the basic input / output system; selecting some configuration combinations from the multiple configuration combinations, invoking an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collecting the corresponding energy efficiency test results output by the energy efficiency test tool; the similarity degree of the energy efficiency test results between the non-full-load test and the full-load test is greater than a preset threshold; using an energy efficiency prediction model to perform energy efficiency prediction on the configuration combinations that do not have corresponding energy efficiency test results among the multiple configuration combinations, and collecting the corresponding energy efficiency prediction results.

[0249] In this embodiment, when the processor executes the computer program stored in the memory, the following steps can be specifically implemented: summarizing and analyzing multiple configuration combinations and their corresponding energy efficiency prediction results to determine the influence relationship between the configuration values corresponding to each to-be-tested configuration item among the multiple configuration combinations and the corresponding energy efficiency prediction results; using curve visualization to display multiple configuration combinations and their corresponding energy efficiency prediction results.

[0250] Furthermore, an embodiment of the present invention further provides an electronic device. Among them, the above electronic device can be either a Figure 8 server as shown, or a Figure 9 terminal as shown. Figure 8 and Figure 9 are both structural diagrams of an electronic device shown according to an exemplary embodiment, and the content in the figure cannot be considered as any limitation on the usage scope of the present invention.

[0251] Figure 8 is a schematic structural diagram of a server provided by an embodiment of the present invention. The server can specifically include: at least one processor, at least one memory, a power supply, a communication interface, an input / output interface, and a communication bus. Among them, the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the relevant steps in the model training disclosed in any of the foregoing embodiments.

[0252] In this embodiment, the power supply is used to provide working voltage for each hardware device on the server; the communication interface can create a data transmission channel between the server and external devices, and the communication protocol it follows is any communication protocol that can be applicable to the technical solution of the present invention, and no specific limitation is imposed on it here; the input / output interface is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and no specific limitation is made here.

[0253] In addition, as a carrier for storing resources, the memory can be a read-only memory, a random access memory, a magnetic disk, an optical disc, etc. The resources stored thereon include an operating system, computer programs, data, etc., and the storage method can be temporary storage or permanent storage.

[0254] Among them, the operating system is used to manage and control each hardware device and computer program on the server to enable the processor to perform operations and processing on the data in the memory. It can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program capable of implementing the model training method disclosed in any of the foregoing embodiments, the computer program may further include a computer program capable of performing other specific tasks. In addition to data such as update information of the application program, the data may further include data such as developer information of the application program.

[0255] Figure 9 The following is a schematic structural diagram of a terminal provided by an embodiment of the present invention. Specifically, the terminal may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.

[0256] Generally, the terminal in this embodiment includes: a processor and a memory.

[0257] Among them, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may further include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0258] The memory may include one or more computer non-volatile storage media, which may be non-transitory. The memory may also include high-speed random access memory, as well as non-volatile memory, such as one or more disk storage devices and flash storage devices. In this embodiment, the memory is at least used to store the following computer programs. After the computer programs are loaded and executed by the processor, the relevant steps in the model training and / or energy efficiency prediction methods executed by the terminal side disclosed in any of the foregoing embodiments can be implemented. In addition, the resources stored in the memory may also include an operating system and data, etc., and the storage method may be transient storage or permanent storage. Among them, the operating system may include Windows, Unix, Linux, etc. The data may include, but is not limited to, update information of application programs.

[0259] In some embodiments, the terminal may further include a display screen, an input / output interface, a communication interface, sensors, a power supply, and a communication bus.

[0260] Those skilled in the art can understand that Figure 9 the structure shown in does not constitute a limitation on the terminal, and it may include more or fewer components than those shown in the figure.

[0261] Next, a non-volatile storage medium provided by an embodiment of the present invention will be introduced. The non-volatile storage medium described below may be referred to in combination with other embodiments described herein.

[0262] A non-volatile storage medium is used to store a computer program. When the computer program is executed by a processor, the model training and / or energy efficiency prediction methods disclosed in the foregoing embodiments are implemented. Among them, the non-volatile storage medium is a computer-readable non-volatile storage medium. As a carrier for storing resources, it may be a read-only memory, a random access memory, a disk, or an optical disc, etc. The resources stored thereon include an operating system, a computer program, and data, etc., and the storage method may be transient storage or permanent storage.

[0263] Next, a computer program product provided by an embodiment of the present invention will be introduced. The computer program product described below may be referred to in combination with other embodiments described herein.

[0264] A computer program product includes computer programs / instructions. When the computer programs / instructions are executed by a processor, the steps of the model training and / or energy efficiency prediction methods disclosed above are implemented.

[0265] The various embodiments in this specification are described in a progressive manner. The key points of each embodiment are the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0266] The steps of the methods or algorithms described in connection with the embodiments disclosed herein may be implemented directly in hardware, in software modules executed by a processor, or in a combination thereof. The software modules may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of non-volatile storage medium known in the art.

[0267] Specific examples are used in this article to illustrate the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on the present invention.

Claims

1. A model training method, characterized in that, Applied to a test control system, including: Determine multiple configuration combinations formed by each configuration item to be tested in the basic input / output system; Select some configuration combinations from the multiple configuration combinations, call an energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, and collect the corresponding energy efficiency test results output by the energy efficiency test tool; sort the multiple configuration combinations; use the configuration combinations arranged in even positions in the obtained target sequence as the selected configuration combinations; or use the configuration combinations arranged in odd positions in the obtained target sequence as the selected configuration combinations; The similarity degree of the energy efficiency test results between the non-full-load test and the full-load test is greater than a preset threshold; Construct the selected configuration combinations and the corresponding energy efficiency test results into the same data group to obtain multiple data groups; Construct model training data based on adjacent data groups among the multiple data groups, and use the model training data to train an energy efficiency prediction model; arrange multiple configuration combinations; construct multiple model application data in units of a set number of combinations in the obtained sequence; when the energy efficiency prediction model performs energy efficiency prediction for a model application data, refer to the energy efficiency test results of the adjacent configuration combinations of the configuration combination to be predicted in the current model application data; Select some test tasks from each test task corresponding to the full-load test for non-full-load test, including: Randomly select test tasks from the various test tasks according to the random selection strategy configured in the task configuration file of the energy efficiency test tool as candidate tasks; Call the energy efficiency test tool to run the candidate tasks to perform a non-full-load test on the selected configuration combinations, and collect the corresponding energy efficiency test results output by the energy efficiency test tool; Select the energy efficiency test results with a similarity degree greater than the preset threshold to the energy efficiency test results of the full-load test from the obtained energy efficiency test results as optional results to screen the test tasks with the most consistent change trend of the full-load performance energy consumption ratio for each test task; Use the candidate tasks corresponding to the optional results as the selected test tasks and perform a non-full-load test.

2. The method according to claim 1, wherein Determine multiple configuration combinations formed by each configuration item to be tested in the basic input / output system, including: Determine each configuration item to be tested in the basic input / output system and the configuration values corresponding to each configuration item to be tested respectively; Perform non-repetitive combinations on the configuration values corresponding to each configuration item to be tested respectively to obtain the multiple configuration combinations.

3. The method according to claim 1, wherein Select some configuration combinations from the multiple configuration combinations, including: Select some configuration combinations from the multiple configuration combinations according to a preset ratio; the preset ratio is not less than fifty percent.

4. The method according to claim 1, wherein Call the energy efficiency test tool to perform a non-full-load test on the selected configuration combinations, including: According to the task configuration file of the energy efficiency test tool, determine each test task corresponding to the full-load test, and select some test tasks from the various test tasks; Call the energy efficiency test tool to run the selected test tasks to perform a non-full-load test on the selected configuration combinations.

5. The method according to claim 4, characterized in that, Select some test tasks from the various test tasks, including: Select some test tasks from the various test tasks according to the non-full-load test table preset in the task configuration file.

6. The method according to claim 1, wherein The selected configuration combinations and corresponding energy efficiency test results are constructed into the same data group, and multiple data groups are obtained, including: The selected configuration combination is combined with the corresponding energy efficiency test results to obtain corresponding multiple data groups.

7. The method according to any one of claims 1 to 6, characterized in that Constructing model training data based on adjacent data groups in the multiple data groups includes: Set the unit data size; Determining the number of data groups included in the adjacent data group according to the unit data size; A plurality of the model training data are constructed in the plurality of data groups with the number of the data groups as a unit.

8. The method according to claim 7, wherein The number of data groups is 3; Accordingly, in the plurality of data groups, a plurality of the model training data are constructed with the number of the data groups as a unit, including: Every three adjacent data groups among the multiple data groups are spliced in sequence.

9. The method according to claim 8, wherein Sequentially splicing every three adjacent data groups in the plurality of data groups, comprising: Each data group in the multiple data groups is converted into a one-hot code, and the one-hot codes of every three adjacent data groups are concatenated in sequence.

10. The method according to any one of claims 1 to 6, characterized in that, The energy efficiency prediction model is obtained by training the model training data, including: Inputting the model training data into a deep learning model so that the deep learning model outputs corresponding training energy efficiency results; Calculating a loss value between the training energy efficiency result and a preset energy efficiency label of the model training data; If the loss value meets the preset model convergence condition, the current deep learning model is used as the energy efficiency prediction model.

11. The method according to claim 10, wherein If the loss value does not meet the model convergence condition, the model parameters of the current deep learning model are iteratively updated using the loss value until the loss value meets the model convergence condition.

12. The method according to any one of claims 1 to 6, characterized in that After the energy efficiency prediction model is obtained by training the model training data, the method further includes: Model application data is constructed based on the multiple configuration combinations.

13. An energy efficiency prediction method, characterized in that, include: Determine multiple configuration combinations formed by configuration items to be tested of the basic input and output system; Selecting some configuration combinations from the multiple configuration combinations, calling an energy efficiency test tool to perform a non-full load test on the selected configuration combinations, and collecting corresponding energy efficiency test results output by the energy efficiency test tool; the degree of similarity between the energy efficiency test results of the non-full load test and the full load test is greater than a preset threshold; Using the energy efficiency prediction model, performing energy efficiency prediction on the configuration combinations for which there are no corresponding energy efficiency test results among the multiple configuration combinations, and collecting corresponding energy efficiency prediction results; Wherein, the energy efficiency prediction model is obtained based on the model training method described in any one of claims 1 to 12.

14. The method according to claim 13, characterized in that, Also includes: Summarizing and analyzing the multiple configuration combinations and their corresponding energy efficiency prediction results to determine the influence relationship between the configuration values corresponding to the configuration items to be tested in the multiple configuration combinations and the corresponding energy efficiency prediction results; The multiple configuration combinations and their corresponding energy efficiency prediction results are visualized using curves.

15. An electronic device, characterized in that, include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the method according to any one of claims 1 to 14.

16. A non-volatile storage medium, characterized in that, Used to store a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 14 is implemented.

17. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 14 is implemented.

Images